© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 7615
    Prev
    Next
    INDEX
    Explanations

    references to different forms or versions of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe different manifestations or types of a particular concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orsi
    -0.64
    incial
    -0.62
     Restaur
    -0.60
    annis
    -0.60
    iolet
    -0.60
    aren
    -0.56
     VIDEOS
    -0.55
    yright
    -0.54
    oner
    -0.54
     Bounce
    -0.53
    POSITIVE LOGITS
    aldehyde
    1.32
    ulating
    1.01
    ulated
    0.86
    fitting
    0.84
    ative
    0.80
    ulates
    0.77
    ulator
    0.77
    idable
    0.76
     of
    0.72
    ulation
    0.71
    Activations Density 0.028%

    No Known Activations